Human visual grouping processes consolidate independent visual objects into grouped visual features on the basis of shared characteristics; these visual features can themselves be grouped, resulting in a hierarchical representation of visual grouping information. This “grouping hierarchy“ promotes ef- ficient attention in the support of goal-directed behavior, but improper grouping of elements of a visual scene can also re- sult in critical behavioral errors. Understanding of how visual object/features characteristics such as size and form influences perception of hierarchical visual groups can further theory of human visual grouping behavior and contribute to effective in- terface design. In the present study, participants provided free- response groupings of a set of stimuli that contained consistent structural relationships between a limited set of visual features. These grouping patterns were evaluated for relationships be- tween specific characteristics of the constituent visual features and the distribution of features across levels of the indicated grouping hierarchy. We observed that while the relative size of the visual features differentiated groupings across levels of the grouping hierarchy, the form of visual objects and features was more likely to distinguish separate groups within a partic- ular level of hierarchy. These consistent relationships between visual feature characteristics and placement within a grouping hierarchy can be leveraged to advance computational theories of human visual grouping behavior, which can in turn be ap- plied to effective design for interfaces such as voter ballots.
more »
« less
Supervised learning of large perceptual organization: graph spectral partitioning and learning automata
Perceptual organization offers an elegant framework to group low-level features that are likely to come from a single object. We offer a novel strategy to adapt this grouping process to objects in a domain. Given a set of training images of objects in context, the associated learning process decides on the relative importance of the basic salient relationships such as proximity, parallelness, continuity, junctions, and common region toward segregating the objects from the background. The parameters of the grouping process are cast as probabilistic specifications of Bayesian networks that need to be learned. This learning is accomplished using a team of stochastic automata in an N-player cooperative game framework. The grouping process, which is based on graph partitioning is able to form large groups from relationships defined over a small set of primitives and is fast. We statistically demonstrate the robust performance of the grouping and the learning frameworks on a variety of real images. Among the interesting conclusions is the significant role of photometric attributes in grouping and the ability to form large salient groups from a set of local relations, each defined over a small number of primitives.
more »
« less
- Award ID(s):
- 9907141
- PAR ID:
- 10346818
- Date Published:
- Journal Name:
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Volume:
- 22
- Issue:
- 5
- ISSN:
- 0162-8828
- Page Range / eLocation ID:
- 504 to 525
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Human visual grouping processes consolidate independent visual objects into grouped visual features on the basis of shared characteristics; these visual features can themselves be grouped, resulting in a hierarchical representation of visual grouping information. This “grouping hierarchy“ promotes ef- ficient attention in the support of goal-directed behavior, but improper grouping of elements of a visual scene can also re- sult in critical behavioral errors. Understanding of how visual object/features characteristics such as size and form influences perception of hierarchical visual groups can further theory of human visual grouping behavior and contribute to effective in- terface design. In the present study, participants provided free- response groupings of a set of stimuli that contained consistent structural relationships between a limited set of visual features. These grouping patterns were evaluated for relationships be- tween specific characteristics of the constituent visual features and the distribution of features across levels of the indicated grouping hierarchy. We observed that while the relative size of the visual features differentiated groupings across levels of the grouping hierarchy, the form of visual objects and features was more likely to distinguish separate groups within a partic- ular level of hierarchy. These consistent relationships between visual feature characteristics and placement within a grouping hierarchy can be leveraged to advance computational theories of human visual grouping behavior, which can in turn be ap- plied to effective design for interfaces such as voter ballots.more » « less
-
Abbott, Derek (Ed.)more » « less
Abstract Human vision, thought, and planning involve parsing and representing objects and scenes using structured representations based on part-whole hierarchies. Computer vision and machine learning researchers have recently sought to emulate this capability using neural networks, but a generative model formulation has been lacking. Generative models that leverage compositionality, recursion, and part-whole hierarchies are thought to underlie human concept learning and the ability to construct and represent flexible mental concepts. We introduce Recursive Neural Programs (RNPs), a neural generative model that addresses the part-whole hierarchy learning problem by modeling images as hierarchical trees of probabilistic sensory-motor programs. These programs recursively reuse learned sensory-motor primitives to model an image within different spatial reference frames, enabling hierarchical composition of objects from parts and implementing a grammar for images. We show that RNPs can learn part-whole hierarchies for a variety of image datasets, allowing rich compositionality and intuitive parts-based explanations of objects. Our model also suggests a cognitive framework for understanding how human brains can potentially learn and represent concepts in terms of recursively defined primitives and their relations with each other.
-
Humans can learn complex functional relationships between variables from small amounts of data. In doing so, they draw on prior expectations about the form of these relationships. In three experiments, we show that people learn to adjust these expectations through experience, learning about the likely forms of the functions they will encounter. Previous work has used Gaussian processes—a statistical framework that extends Bayesian nonparametric approaches to regression—to model human function learning. We build on this work, modeling the process of learning to learn functions as a form of hierarchical Bayesian inference about the Gaussian process hyperparameters.more » « less
-
Ensemble learning, in its simplest form, entails the training of multiple models with the same training set. In a standard supervised setting, the training set can be viewed as a 'teacher' with an unbounded capacity of interactions with a single group of 'trainee' models. One can then ask the following broad question: How can we train an ensemble if the teacher has a bounded capacity of interactions with the trainees? Towards answering this question we consider how humans learn in peer groups. The problem of how to group individuals in order to maximize outcomes via cooperative learning has been debated for a long time by social scientists and policymakers. More recently, it has attracted research attention from an algorithmic standpoint which led to the design of grouping policies that appear to result in better aggregate learning in experiments with human subjects. Inspired by human peer learning, we hypothesize that using partially trained models as teachers to other less accurate models, i.e.~viewing ensemble learning as a peer process, can provide a solution to our central question. We further hypothesize that grouping policies, that match trainer models with learner models play a significant role in the overall learning outcome of the ensemble. We present a formalization and through extensive experiments with different types of classifiers, we demonstrate that: (i) an ensemble can reach surprising levels of performance with little interaction with the training set (ii) grouping policies definitely have an impact on the ensemble performance, in agreement with previous intuition and observations in human peer learning.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/34.857006
